# Co-localization with Category-Consistent Features and Geodesic Distance Propagation

arXiv: https://arxiv.org/abs/1612.03236 · HTML: https://mlsanity.com/paper/1612.03236/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2016.

## Built on by (most cited first, 14 of 14)

- [Zero-shot Object Counting](https://mlsanity.com/paper/2303.02001/) (2023)
- [From Shadow Generation to Shadow Removal](https://mlsanity.com/paper/2103.12997/) (2021)
- [Generating Representative Samples for Few-Shot Classification](https://mlsanity.com/paper/2205.02918/) (2022)
- [Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection](https://mlsanity.com/paper/2304.05096/) (2023)
- [Beyond Pixels: Semi-Supervised Semantic Segmentation with a Multi-scale Patch-based Multi-Label Classifier](https://mlsanity.com/paper/2407.04036/) (2024)
- [Unsupervised and semi-supervised co-salient object detection via segmentation frequency statistics](https://mlsanity.com/paper/2311.06654/) (2023)
- [Shadow Removal Refinement via Material-Consistent Shadow Edges](https://mlsanity.com/paper/2409.06848/) (2024)
- [Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy](https://mlsanity.com/paper/2411.00868/) (2024)
- [Weighting Pseudo-Labels via High-Activation Feature Index Similarity and Object Detection for Semi-Supervised Segmentation](https://mlsanity.com/paper/2407.12630/) (2024)
- [Self-supervised co-salient object detection via feature correspondence at multiple scales](https://mlsanity.com/paper/2403.11107/) (2024)
- [TF-SSD: A Strong Pipeline via Synergic Mask Filter for Training-free Co-salient Object Detection](https://mlsanity.com/paper/2604.00549/) (2026)
- [Single Stage Class Agnostic Common Object Detection: A Simple Baseline](https://mlsanity.com/paper/2104.12245/) (2021)
- [A Feature Generator for Few-Shot Learning](https://mlsanity.com/paper/2409.14141/) (2024)
- [Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoning](https://mlsanity.com/paper/2512.06179/) (2025)

## Abstract (arXiv)

Co-localization is the problem of localizing objects of the same class using only the set of images that contain them. This is a challenging task because the object detector must be built without negative examples that can lead to more informative supervision signals. The main idea of our method is to cluster the feature space of a generically pre-trained CNN, to find a set of CNN features that are consistently and highly activated for an object category, which we call category-consistent CNN features. Then, we propagate their combined activation map using superpixel geodesic distances for co-localization. In our first set of experiments, we show that the proposed method achieves state-of-the-art performance on three related benchmarks: PASCAL 2007, PASCAL-2012, and the Object Discovery dataset. We also show that our method is able to detect and localize truly unseen categories, on six held-out ImageNet categories with accuracy that is significantly higher than previous state-of-the-art. Our intuitive approach achieves this success without any region proposals or object detectors and can be based on a CNN that was pre-trained purely on image classification tasks without further fine-tuning.