Related papers: STEP: Learning N:M Structured Sparsity Masks from …

We study optimization for losses that admit a variance-mean scale-mixture representation. Under this representation, each EM iteration is a weighted least squares update in which latent variables determine observation and parameter weights;…

Instance segmentation demands costly per-pixel annotations and computationally expensive models. We introduce CAST, a semi-supervised knowledge distillation (SSKD) framework that compresses pre-trained vision foundation models (VFM) into…

This paper presents a Spatial Re-parameterization (SpRe) method for the N:M sparsity. SpRe stems from an observation regarding the restricted variety in spatial sparsity of convolution kernels presented in N:M sparsity compared with…

Continual Learning with Pre-trained Models holds great promise for efficient adaptation across sequential tasks. However, most existing approaches freeze PTMs and rely on auxiliary modules like prompts or adapters, limiting model plasticity…

The absence of large-scale masked face datasets challenges masked face detection and recognition. We propose a two-step generative data augmentation framework combining rule-based mask warping with unpaired image-to-image translation via…

In this paper, we introduce InstructSAM, a unified and streamlined framework designed for multi-instance segmentation under arbitrary instructions. We formulates instruction-driven instance segmentation as a set-structured query prediction…

Recently, tactile sensing has attracted great interest in robotics, especially for facilitating exploration of unstructured environments and effective manipulation. A detailed understanding of the surface textures via tactile sensing is…

Class incremental semantic segmentation aims to preserve old knowledge while learning new tasks, however, it is impeded by catastrophic forgetting and background shift issues. Prior works indicate the pivotal importance of initializing new…

Surface defect detection is a critical task across numerous industries, aimed at efficiently identifying and localising imperfections or irregularities on manufactured components. While numerous methods have been proposed, many fail to meet…

Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While recent work on efficient reasoning reduces this overhead…

Self-supervised learning has been proved to benefit a wide range of speech processing tasks, such as speech recognition/translation, speaker verification and diarization, etc. However, most of current approaches are computationally…

Scaling up network depth is a fundamental pursuit in neural architecture design, as theory suggests that deeper models offer exponentially greater capability. Benefiting from the residual connections, modern neural networks can scale up to…

Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training…

The Segment Anything Model (SAM) achieves remarkable promptable segmentation given high-quality prompts which, however, often require good skills to specify. To make SAM robust to casual prompts, this paper presents the first comprehensive…

Sharpness-Aware Minimization (SAM) improves model generalization but doubles the computational cost of Stochastic Gradient Descent (SGD) by requiring twice the gradient calculations per optimization step. To mitigate this, we propose…

Scene Text Recognition requires modeling visual structures that evolve from coarse layouts to fine-grained character strokes. Training such models relies on large amounts of annotated data. Recent self-supervised approaches, such as Masked…

Sharpness-aware minimization (SAM) seeks the minima with a flat loss landscape to improve the generalization performance in machine learning tasks, including fine-tuning. However, its extra parameter perturbation step doubles the…

Multivariate time series modeling and prediction problems are abundant in many machine learning application domains. Accurate interpretation of such prediction outcomes from a machine learning model that explicitly captures temporal…

Diffusion Probabilistic Models (DPMs) have achieved great success in image generation but suffer from high inference latency due to their iterative denoising nature. Motivated by the evolving feature dynamics across the denoising…

Masked diffusion models (MDMs) are a promising alternative to autoregressive models (ARMs), but they suffer from inherently much higher training variance. High variance leads to noisier gradient estimates and unstable optimization, so even…