The paper revisits feature inversion via inverse networks, proposing a modular variant that is computationally efficient and can produce more semantically coherent image reconstructions. It applies this method to large‑scale transformer‑based vision models—Detection Transformer, Vision Transformer, Swin Transformer, and Data‑Efficient Image Transformer—examining reconstructions across network depth. The analysis highlights gradual representational changes in Detection and Vision Transformers, systematic differences in preserving contextual shape and fine‑grained details, and varying robustness to color perturbations, while also demonstrating the framework’s broader applicability to other transformer architectures.
arXiv:2204. 14224v3 Announce Type: replace-cross Abstract: The automated analysis of heterogeneous natural textures is frequently hindered by physical damage and data loss, presenting a significant challenge to computer vision.
arXiv:2511. 17688v2 Announce Type: replace-cross Abstract: Input transformation-based attacks improve adversarial transferability by aggregating gradients over transformed inputs.
arXiv:2608. 20134v1 Announce Type: cross Abstract: We present a novel view on feature evolution in Vision Transformers (ViTs) by visualizing the training process over two dimensions -- network depth (layer) and training time (epochs).
Vision Transformers underperform convolutional networks when training data is scarce, and distilling convolutional inductive biases from a CNN teacher is an effective remedy that leaves the deployed model unchanged. General-purpose feature distillation, however, transfers little in this setting.
The paper presents a detailed study of feature representations in Vision Transformers (ViTs), revealing that feature collapse at initialization causes redundancy and proposing a reduction scheme to address it. It demonstrates that entropy and minimum eigenvalue metrics reliably predict generalization, and that token‑space features and linear submodule outputs are particularly informative. The authors develop a proxy that improves ranking of ViT architectures by 18‑48% over previous baselines, enabling the selection of models with higher accuracy at comparable or lower computational cost.
arXiv:2608. 01298v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) have emerged as a core architecture in generative modeling due to their scalability and adaptability to multimodal tasks.
GaLe is a memory‑efficient technique that allows pretrained neural networks to run on resource‑constrained devices without retraining. It splits feature maps into a local exact component that keeps fine details and a global approximate component that preserves long‑range dependencies, enabling global operations and attention mechanisms typical of hybrid CNN‑transformer models. On ImageNet, GaLe matches exact‑inference accuracy while delivering up to 65% speedup and 90% RAM reduction on a Cortex‑M33, and it works across classification, detection, and generation tasks.
arXiv:2606. 25318v1 Announce Type: cross Abstract: In this paper, we propose a discrete roto-reflection group equivariant vision transformer with convolutional attention.
arXiv:2607. 00774v1 Announce Type: cross Abstract: Recent recursive Transformer studies have primarily reused shared parameters across computation steps to construct compact, parameter-efficient models.
arXiv:2505.16157v3 Announce Type: replace Abstract: Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Tran...
arXiv:2511. 12810v2 Announce Type: replace-cross Abstract: Camouflaged object detection is an emerging and challenging computer vision task that requires identifying and segmenting objects that blend seamlessly into their environments due to high similarity in color, texture, and size.
The paper introduces reViT, a recurrent vision transformer that uses a single Transformer block repeatedly to achieve the accuracy of a full-depth encoder while keeping inference FLOPs comparable. It achieves depth‑specific transformations by expressing each block’s feed‑forward network as a convex combination of a small shared expert bank, with a continuous depth coordinate guiding the mixture. Experiments on ImageNet‑1k and DINOv2 distillation show that reViT matches or surpasses state‑of‑the‑art models, reduces stored parameters by about 70%, and supports elastic‑depth deployment from a single checkpoint.