In this paper, we introduce a novel self-supervised learning (SSL) loss for
image representation learning. There is a growing belief that generalization in
deep neural networks is linked to their ability to discriminate object shapes.
Since object shape is related to the location of its parts, we propose to
detect those that have been artificially misplaced. We represent object parts
with image tokens and train a ViT to detect which token has been combined with
an incorrect positional embedding. We then introduce sparsity in the inputs to
make the model more robust to occlusions and to speed up the training. We call
our method DILEMMA, which stands for Detection of Incorrect Location EMbeddings
with MAsked inputs. We apply DILEMMA to MoCoV3, DINO and SimCLR and show an
improvement in their performance of respectively 4.41%, 3.97%, and 0.5% under
the same training time and with a linear probing transfer on ImageNet-1K. We
also show full fine-tuning improvements of MAE combined with our method on
ImageNet-100. We evaluate our method via fine-tuning on common SSL benchmarks.
Moreover, we show that when downstream tasks are strongly reliant on shape
(such as in the YOGA-82 pose dataset), our pre-trained features yield a
significant gain over prior work.

本文提出了一种名为 DILEMMA 的方法，通过使用自监督学习来提高图像表征的性能。该方法使用图像令牌来代表物体的部分，并训练一个 ViT 模型来检测人为移位的图像令牌，从而提高鲁棒性和训练速度，并通过在 ImageNet-1K 上进行线性探测转移，在 MoCoV3、DINO 和 SimCLR 模型中分别实现 4.41％，3.97％和 0.5％的性能提高。

通过检测不正确位置嵌入进行表示学习

Representation Learning by Detecting Incorrect Location Embeddings

Vision Transformers (ViTs) take all the image patches as tokens and construct
multi-head self-attention (MHSA) among them. Complete leverage of these image
tokens brings redundant computations since not all the tokens are attentive in
MHSA. Examples include that tokens containing semantically meaningless or
distractive image backgrounds do not positively contribute to the ViT
predictions. In this work, we propose to reorganize image tokens during the
feed-forward process of ViT models, which is integrated into ViT during
training. For each forward inference, we identify the attentive image tokens
between MHSA and FFN (i.e., feed-forward network) modules, which is guided by
the corresponding class token attention. Then, we reorganize image tokens by
preserving attentive image tokens and fusing inattentive ones to expedite
subsequent MHSA and FFN computations. To this end, our method EViT improves
ViTs from two perspectives. First, under the same amount of input image tokens,
our method reduces MHSA and FFN computation for efficient inference. For
instance, the inference speed of DeiT-S is increased by 50% while its
recognition accuracy is decreased by only 0.3% for ImageNet classification.
Second, by maintaining the same computational cost, our method empowers ViTs to
take more image tokens as input for recognition accuracy improvement, where the
image tokens are from higher resolution images. An example is that we improve
the recognition accuracy of DeiT-S by 1% for ImageNet classification at the
same computational cost of a vanilla DeiT-S. Meanwhile, our method does not
introduce more parameters to ViTs. Experiments on the standard benchmarks show
the effectiveness of our method. The code is available at
this https URL

本论文提出了一种在 Vision Transformer 模型的前向推理过程中重新组织图像 tokens 的方法，以提高模型的计算效率和识别准确率。结果表明，该方法能够在保持相同的计算成本的前提下，提高模型的输入规模并提高模型的识别准确率。