TriLite: Efficient Weakly Supervised Object Localization with Universal Visual Features and Tri-Region Disentanglement

TL;DR

TriLite introduces a single-stage, parameter-efficient weakly supervised object localization framework leveraging a frozen Vision Transformer with a novel TriHead module for improved object coverage and state-of-the-art results.

Contribution

It proposes TriLite, a novel WSOL method using minimal trainable parameters and a disentanglement approach to improve object localization without extensive fine-tuning.

Findings

Sets new state-of-the-art on multiple datasets

Uses fewer than 800K trainable parameters

Easier to train than prior WSOL methods

Abstract

Weakly supervised object localization (WSOL) aims to localize target objects in images using only image-level labels. Despite recent progress, many approaches still rely on multi-stage pipelines or full fine-tuning of large backbones, which increases training cost, while the broader WSOL community continues to face the challenge of partial object coverage. We present TriLite, a single-stage WSOL framework that leverages a frozen Vision Transformer with Dinov2 pre-training in a self-supervised manner, and introduces only a minimal number of trainable parameters (fewer than 800K on ImageNet-1K) for both classification and localization. At its core is the proposed TriHead module, which decomposes patch features into foreground, background, and ambiguous regions, thereby improving object coverage while suppressing spurious activations. By disentangling classification and localization objectives, TriLite effectively exploits the universal representations learned by self-supervised ViTs without requiring expensive end-to-end training. Extensive experiments on CUB-200-2011, ImageNet-1K, and OpenImages demonstrate that TriLite sets a new state of the art, while remaining significantly more parameter-efficient and easier to train than prior methods. The code will be released soon.