# Learning from Counting: Leveraging Temporal Classification for Weakly Supervised Object Localization and Detection

arXiv: https://arxiv.org/abs/2103.04009 · HTML: https://mlsanity.com/paper/2103.04009/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 6 Mar 2021.

## Builds on (most cited first, 18 of 18)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Weakly Supervised Deep Detection Networks](https://mlsanity.com/paper/1511.02853/) (2015)
- [Multiple Instance Detection Network with Online Instance Classifier Refinement](https://mlsanity.com/paper/1704.00138/) (2017)
- [PCL: Proposal Cluster Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1807.03342/) (2018)
- [Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks](https://mlsanity.com/paper/1512.04143/) (2015)
- [C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1904.05647/) (2019)
- [Deep Contrast Learning for Salient Object Detection](https://mlsanity.com/paper/1603.01976/) (2016)
- [Weakly Supervised Cascaded Convolutional Networks](https://mlsanity.com/paper/1611.08258/) (2016)
- [Towards Precise End-to-end Weakly Supervised Object Detection Network](https://mlsanity.com/paper/1911.12148/) (2019)
- [Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning](https://mlsanity.com/paper/1503.00949/) (2015)
- [What makes for effective detection proposals?](https://mlsanity.com/paper/1502.05082/) (2015)
- [Scalable Object Detection using Deep Neural Networks](https://mlsanity.com/paper/1312.2249/) (2013)
- [ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks](https://mlsanity.com/paper/1505.00393/) (2015)
- [C-WSL: Count-guided Weakly Supervised Localization](https://mlsanity.com/paper/1711.05282/) (2017)
- [Object-Proposal Evaluation Protocol is 'Gameable'](https://mlsanity.com/paper/1505.05836/) (2015)

## Built on by (most cited first, 5 of 5)

- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition](https://mlsanity.com/paper/2109.04145/) (2021)
- [Segment Anything Model Can Not Segment Anything: Assessing AI Foundation Model's Generalizability in Permafrost Mapping](https://mlsanity.com/paper/2401.08787/) (2024)
- [Tobler's First Law in GeoAI: A Spatially Explicit Deep Learning Model for Terrain Feature Detection Under Weak Supervision](https://mlsanity.com/paper/2508.03745/) (2025)
- [GeoAI in Social Science](https://mlsanity.com/paper/2401.05398/) (2023)

## Abstract (arXiv)

This paper reports a new solution of leveraging temporal classification to support weakly supervised object detection (WSOD). Specifically, we introduce raster scan-order techniques to serialize 2D images into 1D sequence data, and then leverage a combined LSTM (Long, Short-Term Memory) and CTC (Connectionist Temporal Classification) network to achieve object localization based on a total count (of interested objects). We term our proposed network LSTM-CCTC (Count-based CTC). This "learning from counting" strategy differs from existing WSOD methods in that our approach automatically identifies critical points on or near a target object. This strategy significantly reduces the need of generating a large number of candidate proposals for object localization. Experiments show that our method yields state-of-the-art performance based on an evaluation on PASCAL VOC datasets.