ResNet

ResNet：深度学习的“高速公路”——让AI看得更深更准

在人工智能的浪潮中，我们常常惊叹于AI在图像识别、自动驾驶、医疗诊断等领域展现出的超凡能力。这些能力的背后，离不开一种被称为“深度学习”的技术，而深度学习中，又有一种关键的“神经网络”架构，它的出现，如同在AI学习的道路上，开辟了一条条“高速公路”，让AI得以看得更深、学得更准。这个革新性的架构，就是我们今天要深入探讨的——残差网络（ResNet）。

1. 深度学习的“困境”：越深越好，却也越难学？

想象一下，你正在训练一个“小侦探”辨认图片中的物体。刚开始，你教他一些简单的特征，比如圆形是苹果，方形是盒子。通过几层的“学习”（神经网络的浅层），他表现还不错。于是你觉得，如果让他学得更深入，辨认更多细微的特征，比如苹果的纹理、盒子的材质，那他岂不是会成为“神探”？

在深度学习领域，人们一度认为：神经网络的层数越多，理论上它能学习到的特征就越丰富，性能也应该越好。这就像小侦探学到的知识越多，能力越强。因此，研究人员们疯狂地堆叠神经网络的层数，从十几层到几十层。

然而，现实却并非如此美好。当网络层数达到一定程度后，非但性能没有提升，反而开始下降了。这就像小侦探学了太多复杂的东西，记忆力和理解力反而变差了，甚至会“忘掉”之前学到的简单知识。为什么会这样呢？

这里有两个主要问题：

• 梯度消失/爆炸问题：
  • 消失：想象一下，你给小侦探布置了100道题，每道题的答案都会影响下一道题的答案。如果你在第一道题上犯了个小错误，这个错误经过100次传递后，可能就变得微乎其微，导致你无法有效纠正最初的错误。在神经网络中，每一层都在传递“学习信号”（梯度），如果网络太深，这些信号在反向传播的过程中会逐渐衰减到接近于零，导致前面层的参数无法得到有效更新，学习也就停滞了。
  • 爆炸：反之，如果信号在传递过程中不断放大，就会导致参数更新过快，网络变得不稳定。
• 退化问题（Degradation Problem）：
  • 即使通过一些技术手段解决了梯度消失/爆炸问题，人们发现，简单地增加网络层数，却不改变其基本结构时，深层网络的训练误差反而比浅层网络更高。这表明，深层网络并非总是能学习到更好的“特征表示”，它甚至难以学会一个“恒等映射”（即什么都不学，直接把输入传到输出，保持原样）。如果连“保持原样”都做不到，那学习更复杂的模式就更难了。

这就像你给小侦探安排了200个步骤的复杂任务，他不仅没有变得更聪明，反而连完成简单任务的能力都退步了。

2. ResNet的“脑洞大开”：开辟一条“捷径”

面对这个困境，微软亚洲研究院的何恺明等人于2015年提出了一种革命性的解决方案——残差网络（Residual Network，简称ResNet）。

ResNet的核心思想非常巧妙，它引入了被称为“残差连接（Residual Connection）”或“跳跃连接（Skip Connection）”的机制。

我们不妨用一个更形象的比喻来说明：

假设小侦探要学习识别“猫”这个概念。传统的方法是，你给他一张图片，他从头到尾一层层地分析，比如：
眼睛 -> 鼻子 -> 嘴巴 -> 毛发 -> 整体轮廓 ……然后输出“这是猫”。

如果这个分析过程太长，可能在中间某个环节，他就“迷路”了，或者信息就“失真”了。

ResNet的做法则是在这个分析流程中，加了一条“旁路”或“捷径”。这条捷径是什么呢？

它允许输入数据直接跳过网络中的一层或几层，然后与这些层处理后的输出再进行合并。

具体来说，小侦探在分析图片时，除了原来的层层深入的分析路径，还有一条“直通车”：
他会先把原始图片看一眼（这就是输入 X），然后他有一个“团队”去详细分析这张图（这代表原来的网络层，学习一个复杂的映射 F(X)）。同时，他本人也留了一份原始图片的“副本”（这就是通过捷径传递的 X）。等到团队分析完，他会把团队的分析结果 F(X) 和自己留的原始副本 X 相加，得到最终的结论：F(X) + X。

为什么这样做有用呢？ 关键在于，这样一来，网络不再是直接学习如何从 X 变换到 F(X)+X，而是只需要学习原始输入与期望输出之间的“残差”（F(X)），也就是差异。

这就像：

• 原来（传统网络）：你要小侦探直接从输入 X 学会输出的猫的完整特征 H(X)。如果 H(X) 很难学，他就学不好。
• 现在（ResNet）：你告诉小侦探，你不需要从头生成一张猫的特征图，你只要找到原始图片 X 和目标猫特征图 H(X) 之间的“差异”F(X) 就行了。然后把这个差异 F(X) 加上原始图片 X，就得到了 H(X)。

学习这个“差异”F(X) 往往比直接学习复杂的 H(X) 要容易得多。 甚至在极端情况下，如果原始图片 X 已经足够好，几乎就是猫，那么网络只需要学习 F(X) = 0（即什么都不做），让 H(X) = X 就行了。而学习“什么都不做”的恒等映射，对残差网络来说是轻而易举的。

这种机制有效地缓解了梯度消失问题，因为梯度可以直接通过“捷径”反向传播，确保了前面层也能接收到有效的学习信号。

3. ResNet的威力：更深、更强、更稳定

ResNet的出现，彻底打破了过去深度网络训练的瓶颈，带来了多方面的优势：

• 训练超深网络成为可能：ResNet使得可以构建数百层甚至上千层的深度网络，例如ResNet-50、ResNet-101、ResNet-152等变体，层数越多，通常特征提取能力越强。 在2015年的ImageNet大规模视觉识别挑战赛（ILSVRC）中，ResNet成功训练了高达152层的网络，一举夺得了图像分类、目标检测、物体定位和实例分割等多个任务的冠军。
• 解决梯度消失/爆炸：通过残差连接，梯度可以更容易地流动，使得网络深层的参数也能得到有效更新。
• 模型性能显著提升：在图像分类等任务上，ResNet取得了当时最先进的（state-of-the-art）表现，错误率大幅降低。
• 更容易优化：学习残差函数F(x)通常比学习原始的复杂函数H(x)更容易，训练过程更稳定，收敛速度更快。

4. ResNet的家族与新进展

ResNet并非一成不变，其核心思想启发了众多后续的变体和改进：

• Wide ResNet（WRN）：与其继续增加深度，不如在网络的宽度（即每层通道数）上做文章，可以在减少训练时间的同时，提升模型表达能力。
• DenseNet：通过更密集的连接，让每一层的输出都传递给所有后续层，进一步促进信息和梯度的流动，减少参数量。
• ResNeXt：引入了分组卷积，提出了“cardinality”的概念，通过增加并行路径的数量来提升模型性能。
• SENet（Squeeze-and-Excitation Networks）：在ResNet基础上引入了注意力机制，让网络能够学习每个特征通道的重要性，从而提升特征表达能力。

时至今日，ResNet及其变体仍然是计算机视觉领域不可或缺的基础架构。最新的研究和应用仍在不断涌现：

• 遥感图像分析：2025年的研究展示了ResNet在卫星图像（如Sentinel-2）土地利用分类中的强化应用，通过识别复杂的模式和特征，显著提高分类精度。
• 气候预测：在印度洋偶极子（IOD）的预测研究中，ResNet被用于融合海表温度和海表高度数据，捕捉海洋动力过程，将预测提前期延长至8个月，性能优于传统方法。
• 多领域应用：ResNet在图像分类、目标检测、人脸识别、医疗图像分析（如肺炎预测）、图像分割等多种计算机视觉任务中都表现出强大的能力，并且常作为各种更复杂任务的“骨干网络”（backbone network）来提取特征。
• 结合前沿技术：ResNet也与数据裁剪等技术结合，研究者发现通过对训练样本的挑选，ResNet在训练过程中有可能实现指数级缩放，突破传统幂律缩放的限制。 甚至在2025年，有观点认为，虽然“Transformer巨兽”当道，但诸如ResNet这样的基础架构及其背后的梯度下降原理，仍然是AI进步的“本质方法”，将以更智能、更协同的方式演进。

5. 结语

ResNet的诞生，是深度学习发展史上的一个里程碑。它如同为AI学习搭建了一条条“高速公路”，让信息得以在更深的网络中畅通无阻，有效地解决了深度神经网络训练中的“迷路”和“失忆”问题。它不仅是理论上的突破，更带来了实际应用中性能的显著提升，极大地推动了人工智能，特别是计算机视觉领域的发展。理解ResNet，就是理解AI如何从模仿走向更深的认知，也是领略深度学习魅力的一个绝佳视角。

ResNet: The “Highway” of Deep Learning—Letting AI See Deeper and More Accurately

In the wave of artificial intelligence, we often marvel at AI’s extraordinary abilities in fields like image recognition, autonomous driving, and medical diagnosis. Behind these capabilities lies a technology known as “Deep Learning”, and within deep learning, there is a crucial “neural network” architecture. Its emergence is like opening up “highways” on the path of AI learning, enabling AI to see deeper and learn more accurately. This revolutionary architecture is what we are going to explore in depth today—Residual Network (ResNet).

1. The “Dilemma” of Deep Learning: The Deeper the Better, But Also Harder to Learn?

Imagine you are training a “little detective” to identify objects in pictures. At first, you teach him some simple features, such as circles being apples and squares being boxes. Through a few layers of “learning” (shallow layers of neural networks), he performs quite well. So you think, if you let him learn more deeply and identify more subtle features, such as the texture of apples or the material of boxes, wouldn’t he become a “master detective”?

In the field of deep learning, people once believed: The more layers a neural network has, theoretically the richer the features it can learn, and the better the performance should be. This is like the more knowledge the little detective learns, the stronger his ability. Therefore, researchers frantically stacked the layers of neural networks, from a dozen to dozens of layers.

However, reality was not so wonderful. When the number of network layers reached a certain level, the performance not only did not improve but began to decline. It’s like the little detective learned too many complicated things, and his memory and understanding became worse, even “forgetting” the simple knowledge he learned before. Why does this happen?

There are two main problems here:

• Gradient Vanishing/Exploding Problem:
  • Vanishing: Imagine you assign 100 questions to the little detective, and the answer to each question affects the answer to the next. If you make a small mistake on the first question, this mistake might become negligible after being passed 100 times, causing you to be unable to effectively correct the initial mistake. In neural networks, each layer transmits a “learning signal” (gradient). If the network is too deep, these signals will gradually decay to near zero during backpropagation, causing the parameters of the earlier layers to not be effectively updated, and learning stagnates.
  • Exploding: Conversely, if the signal is constantly amplified during transmission, it will cause the parameters to update too quickly, making the network unstable.
• Degradation Problem:
  • Even if the gradient vanishing/exploding problem is solved by some technical means, people found that when simply increasing the number of network layers without changing its basic structure, the training error of deep networks is actually higher than that of shallow networks. This indicates that deep networks do not always learn better “feature representations”, and they even struggle to learn an “identity mapping” (i.e., learning nothing, just passing the input to the output, keeping it as is). If it can’t even “keep it as is”, then learning more complex patterns is even harder.

This is like assigning a complex task with 200 steps to the little detective; not only did he not become smarter, but his ability to complete simple tasks actually regressed.

2. ResNet’s “Brainstorm”: Opening a “Shortcut”

Faced with this dilemma, He Kaiming and others from Microsoft Research Asia proposed a revolutionary solution in 2015—Residual Network (ResNet).

The core idea of ResNet is very ingenious. It introduces a mechanism called “Residual Connection“ or “Skip Connection“.

Let’s use a more vivid metaphor to explain:

Suppose the little detective needs to learn the concept of “cat”. The traditional method is that you give him a picture, and he analyzes it layer by layer from beginning to end, such as:
Eyes -> Nose -> Mouth -> Fur -> Overall contour… then outputs “This is a cat”.

If this analysis process is too long, he might get “lost” at some link in the middle, or the information might become “distorted”.

ResNet’s approach is to add a “bypass“ or “shortcut“ to this analysis flow. What is this shortcut?

It allows input data to directly skip one or more layers in the network and then merge with the output processed by these layers.

Specifically, when the little detective analyzes a picture, besides the original layer-by-layer indepth analysis path, there is a “direct train”:
He will first take a look at the original picture (this is input $X$), and he has a “team” to analyze this picture in detail (this represents the original network layers, learning a complex mapping $F(X)$). At the same time, he himself also keeps a “copy” of the original picture (this is the input $X$ passed through the shortcut). When the team finishes analyzing, he will add the team’s analysis result $F(X)$ and the original copy $X$ he kept to get the final conclusion: $F(X) + X$.

Why is this useful? The key lies in that, in this way, the network no longer directly learns how to transform from $X$ to $F(X)+X$, but only needs to learn the “residual“ ($F(X)$), which is the difference, between the original input and the expected output.

It’s like:

• Formerly (Traditional Network): You want the little detective to learn the complete features of the cat $H(X)$ directly from input $X$. If $H(X)$ is hard to learn, he won’t learn it well.
• Now (ResNet): You tell the little detective that he doesn’t need to generate a cat feature map from scratch. He just needs to find the “difference“ $F(X)$ between the original picture $X$ and the target cat feature map $H(X)$. Then adding this difference $F(X)$ to the original picture $X$ yields $H(X)$.

Learning this “difference” $F(X)$ is often much easier than directly learning the complex $H(X)$. Even in extreme cases, if the original picture $X$ is already good enough and is almost a cat, then the network only needs to learn $F(X) = 0$ (i.e., do nothing) so that $H(X) = X$. Learning the identity mapping of “doing nothing” is a piece of cake for residual networks.

This mechanism effectively alleviates the gradient vanishing problem because gradients can be backpropagated directly through the “shortcut”, ensuring that earlier layers can also receive effective learning signals.

3. The Power of ResNet: Deeper, Stronger, More Stable

The emergence of ResNet completely broke the bottleneck of deep network training in the past and brought advantages in many aspects:

• Making training ultra-deep networks possible: ResNet makes it possible to build deep networks with hundreds or even thousands of layers, such as variants like ResNet-50, ResNet-101, ResNet-152, etc. The more layers, usually the stronger the feature extraction capability. In the 2015 ImageNet Large Scale Visual Recognition Challenge (ILSVRC), ResNet successfully trained a network with as many as 152 layers and won championships in multiple tasks such as image classification, object detection, object localization, and instance segmentation in one fell swoop.
• Solving Gradient Vanishing/Exploding: Through residual connections, gradients can flow easier, allowing parameters in deep layers of the network to be effectively updated.
• Significant improvement in model performance: On tasks like image classification, ResNet achieved state-of-the-art performance at the time, drastically reducing the error rate.
• Easier to optimize: Learning the residual function $F(x)$ is usually simpler than learning the original complex function $H(x)$, making the training process more stable and convergence faster.

4. ResNet’s Family and New Progress

ResNet is not static; its core ideas have inspired numerous subsequent variants and improvements:

• Wide ResNet (WRN): Instead of continuing to increase depth, it works on the width of the network (i.e., the number of channels per layer), which can improve model expression capability while reducing training time.
• DenseNet: Through denser connections, the output of each layer is passed to all subsequent layers, further promoting the flow of information and gradients, reducing the number of parameters.
• ResNeXt: Introduced grouped convolution and the concept of “cardinality”, improving model performance by increasing the number of parallel paths.
• SENet (Squeeze-and-Excitation Networks): Introduced attention mechanisms on the basis of ResNet, allowing the network to learn the importance of each feature channel, thereby improving feature expression capabilities.

Today, ResNet and its variants remain indispensable infrastructure in the field of computer vision. The latest research and applications are still emerging:

• Remote Sensing Image Analysis: Research in 2025 demonstrates the enhanced application of ResNet in land use classification of satellite images (such as Sentinel-2), significantly improving classification accuracy by identifying complex patterns and features.
• Climate Prediction: In the prediction study of the Indian Ocean Dipole (IOD), ResNet is used to fuse sea surface temperature and sea surface height data, capturing ocean dynamic processes, extending the prediction lead time to 8 months, outperforming traditional methods.
• Multi-domain Applications: ResNet shows strong capabilities in various computer vision tasks such as image classification, object detection, face recognition, medical image analysis (such as pneumonia prediction), and image segmentation, and often serves as the “backbone network” for various more complex tasks to extract features.
• Combining with Frontier Technologies: ResNet is also combined with technologies like data pruning. Researchers found that by selecting training samples, ResNet may achieve exponential scaling during training, breaking the limits of traditional power-law scaling. Even in 2025, there is a view that although “Transformer giants” are prevalent, basic architectures like ResNet and the underlying gradient descent principles are still the “essential methods” of AI progress and will evolve in a smarter and more collaborative way.

5. Conclusion

The birth of ResNet is a milestone in the history of deep learning. It is like building “highways” for AI learning, allowing information to flow unimpeded in deeper networks, effectively solving the “getting lost” and “amnesia” problems in deep neural network training. It is not only a theoretical breakthrough but also brought significant performance improvements in practical applications, greatly promoting the development of artificial intelligence, especially in the field of computer vision. Understanding ResNet is understanding how AI moves from imitation to deeper cognition, and it is also an excellent perspective to appreciate the charm of deep learning.