Related papers: CubistMerge: Spatial-Preserving Token Merging For …
State Space Models (SSMs) have emerged as powerful architectures in computer vision, yet improving their computational efficiency remains crucial for practical and scalable deployment.While token reduction serves as an effective approach…
Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. This representation trades spatial granularity for embedding…
Token compression techniques have recently emerged as powerful tools for accelerating Vision Transformer (ViT) inference in computer vision. Due to the quadratic computational complexity with respect to the token sequence length, these…
Vision Transformer (ViT) has achieved impressive results across various vision tasks, yet its high computational cost limits practical applications. Recent methods have aimed to reduce ViT's $O(n^2)$ complexity by pruning unimportant…
The quadratic cost of self-attention in Vision Transformers (ViTs) constitutes a fundamental bottleneck for practical deployment, motivating a vibrant line of research on token reduction. Among existing approaches, token merging (ToMe) has…
Stable diffusion is an outstanding image generation model for text-to-image, but its time-consuming generation process remains a challenge due to the quadratic complexity of attention operations. Recent token merging methods improve…
Modeling visual data as tokens (i.e., image patches) using attention mechanisms, feed-forward networks or convolutions has been highly effective in recent years. Such methods usually have a common pipeline: a tokenization method, followed…
We propose Confidence-Guided Token Merging (Co-Me), an acceleration mechanism for visual geometric transformers without retraining or finetuning the base model. Co-Me distilled a light-weight confidence predictor to rank tokens by…
In this paper, we present a new approach for model acceleration by exploiting spatial sparsity in visual data. We observe that the final prediction in vision Transformers is only based on a subset of the most informative tokens, which is…
Vision transformers (ViTs) have recently received explosive popularity, but the huge computational cost is still a severe issue. Since the computation complexity of ViT is quadratic with respect to the input sequence length, a mainstream…
Masked Image Modeling (MIM) with Vector Quantization (VQ) has achieved great success in both self-supervised pre-training and image generation. However, most existing methods struggle to address the trade-off in shared latent space for…
Token compression is crucial for mitigating the quadratic complexity of self-attention mechanisms in Vision Transformers (ViTs), which often involve numerous input tokens. Existing methods, such as ToMe, rely on GPU-inefficient operations…
Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed…
Vision Transformer (ViT)-based sparse multi-view 3D object detectors have achieved remarkable accuracy but still suffer from high inference latency due to heavy token processing. To accelerate these models, token compression has been widely…
Vision Transformers (ViTs) can learn strong image-level representations while their patch representations become less effective for dense prediction during prolonged training. We revisit this dense degradation phenomenon and argue that it…
Token merging can effectively accelerate various vision systems by processing groups of similar tokens only once and sharing the results across them. However, existing token grouping methods are often ad hoc and random, disregarding the…
This paper studies how to keep a vision backbone effective while removing token mixers in its basic building blocks. Token mixers, as self-attention for vision transformers (ViTs), are intended to perform information communication between…
Diffusion transformers have shown exceptional performance in visual generation but incur high computational costs. Token reduction techniques that compress models by sharing the denoising process among similar tokens have been introduced.…
Large-scale transformers are central to modern semantic communication, yet their high computational and communication costs hinder deployment on resource-constrained edge devices. This paper introduces a training-free framework for adaptive…
Vision Mambas (ViMs) achieve remarkable success with sub-quadratic complexity, but their efficiency remains constrained by quadratic token scaling with image resolution. While existing methods address token redundancy, they overlook ViMs'…